Jonathan Calvin Limawal, . (2025) IMPLEMENTASI ARSITEKTUR RESNET50 UNTUK KLASIFIKASI HASIL KARAKTERSASI FT-IR PADA SENYAWA ORGANIK. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (233kB) |
|
Text
AWAL.pdf Download (869kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (298kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (931kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (343kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (269kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (247kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (269kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (631kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (8MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (776kB) |
Abstract
One of the main challenges in the discovery or synthesis of natural organic compounds lies in the characterization process. To this day, the interpretation of characterization results—such as FTIR spectra—still heavily relies on manual analysis, making it prone to human error. This study aims to develop a deep learning model based on the ResNet50 architecture to classify functional groups of organic compounds using FTIR characterization data. The FTIR spectral data used in this research were collected from the Spectral Database for Organic Compounds (SDBS) using web scraping techniques. The results show that the developed model performs well, achieving an average test accuracy of 90.59%, with a precision of 0.8877, recall of 0.9025, and F1-score of 0.8943. Additionally, the ResNet50-based model achieved a validation accuracy of 92.54%. Although the dataset used differs, this result exceeds the 83.67% validation accuracy reported by Enders et al., who employed the InceptionV3 architecture to classify six functional groups. This comparison is indicative and highlights the potential of the ResNet50 architecture for similar classification tasks.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511058] [Pembimbing 1: Musthofa Galih Pradana] [Pembimbing 1: Nurul Afifah Arifuddin] [Penguji 1: Supriyanto Praptodiyono] [Penguji 2: Muhammad Adrezo] |
| Uncontrolled Keywords: | FTIR Spectrum, ResNet50, Functional Group Classification, Organic Compound Characterization |
| Subjects: | Q Science > Q Science (General) Q Science > QD Chemistry T Technology > T Technology (General) T Technology > TP Chemical technology |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | JONATHAN CALVIN LIMAWAL |
| Date Deposited: | 07 Aug 2025 01:47 |
| Last Modified: | 07 Aug 2025 01:47 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37300 |
Actions (login required)
 |
View Item |